AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient

Farzad Nikfam, Alberto Marchisio, Maurizio Martina, Muhammad Shafique

Research output: Contribution to journalArticlepeer-review

Abstract

Adversarial training is exploited to develop a robust Deep Neural Network (DNN) model against the malicious altered data. These attacks may have catastrophic effects on DNN models but are indistinguishable for a human being. For example, an external attack can modify an image adding noises invisible for a human eye, but a DNN model misclassifies the image. A key objective for developing robust DNN models is to use a learning algorithm that is fast but can also give model that is robust against different types of adversarial attacks. Especially for adversarial training, enormously long training times are needed for obtaining high accuracy under many different types of adversarial samples generated using different adversarial attack techniques. This paper aims at accelerating the adversarial training to enable fast development of robust DNN models against adversarial attacks. The general method for improving the training performance is the hyperparameters fine-tuning, where the learning rate is one of the most crucial hyperparameters. By modifying its shape (the value over time) and value during the training, we can obtain a model robust to adversarial attacks faster than standard training. First, we conduct experiments on two different datasets (CIFAR10, CIFAR100), exploring various techniques. Then, this analysis is leveraged to develop a novel fast training methodology, <italic>AccelAT</italic>, which automatically adjusts the learning rate for different epochs based on the accuracy gradient. The experiments show comparable results with the related works, and in several experiments, the adversarial training of DNNs using our <italic>AccelAT</italic> framework is conducted up to 2&#x00D7; faster than the existing techniques. Thus, our findings boost the speed of adversarial training in an era in which security and performance are fundamental optimization objectives in DNN-based applications. We will open-source our <italic>AccelAT</italic> framework to facilitate reproducible research.

Original languageEnglish (US)
Pages (from-to)1
Number of pages1
JournalIEEE Access
Volume10
DOIs
StatePublished - 2022

Keywords

  • Adversarial Attack
  • Adversarial machine learning
  • Adversarial Training
  • Data models
  • Deep learning
  • Deep Neural Network (DNN)
  • Fast Training
  • Foolbox
  • Hyperparameters
  • Learning Rate (LR)
  • Learning systems
  • Neural networks
  • Python
  • Robustness
  • TensorFlow
  • Training data

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient'. Together they form a unique fingerprint.

Cite this